© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12741
    Prev
    Next
    INDEX
    Explanations

    complex standardized

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on standalone numeric tokens (i.e., numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ほら
    -0.94
    might
    -0.94
    チョコ
    -0.92
     ボディ
    -0.91
     particolari
    -0.89
    えっ
    -0.88
    お土産
    -0.88
    WANTED
    -0.86
    あー
    -0.85
     ガール
    -0.85
    POSITIVE LOGITS
     then
    1.66
     before
    1.17
     and
    1.13
    ֶ
    1.02
    )--(
    1.01
    Только
    1.00
     Then
    0.99
     शुर
    0.98
    Then
    0.97
    翳
    0.96
    Activations Density 0.000%

    No Known Activations